A model only days into training cannot be known to be aligned, and if such models can leap a generation ahead this fast then training pauses mean little and timelines are shorter than previously thought.

Added to korrents 9 Sept 2026 · How quotes work · Something wrong? Tell us

Related korrents

Our reading — they may agree, disagree or merely touch the same thing. Closest first: a shared subject counts for most, then how near the wording is.

• Very capable AI will be harder to align than current systems, because the loop of spotting a bad behaviour and patching the training that caused it breaks down. RGRyan Greenblatt11 Aug 2026similar wording
• Relying on gradual, continuous shifts in AI training behavior to catch misalignment will eventually fail because the dangerous shift itself may be discontinuous. ZMZvi Mowshowitz2 Sept 2026similar wording
• Alignment of today's models is going well enough to look solvable, while aligning models we can no longer understand remains unsolved. JLJan Leike22 Jan 2026similar wording
• Before building on a gap in the general models, work out whether that gap survives six months or three years. JDJeff Dean30 Jul 2026similar wording
• In this era fluency with AI tools beats years of accumulated experience, so seniority is now a liability rather than an edge. SASam Altman28 Jul 2026similar wording

On the map

Open the map on its own page →